Determining the position and orientation of the camera is a crucial problem with the rapidly developing technology in visual Simultaneous Localization and Mapping(SLAM),augmented reality and 3 D *** the Pn P(perspecti...
详细信息
Determining the position and orientation of the camera is a crucial problem with the rapidly developing technology in visual Simultaneous Localization and Mapping(SLAM),augmented reality and 3 D *** the Pn P(perspective-n-point) problem is an effective method to calculate the pose of the camera and is also the most widely used method in many *** this paper,the methods for Pn P problem,including special Pn P problem and general Pn P problem are summarized ***,due to importance of performing Pn P methods in practical applications,ability to handle outliers for Pn P methods is ***,the main problems of the current researches on Pn P problem are presented.
In modern complex industrial processes,due to poor rationalization of alarm systems and the complexity of process interconnections,alarm floods are commonly *** floods are also identified as the main causes of many in...
详细信息
In modern complex industrial processes,due to poor rationalization of alarm systems and the complexity of process interconnections,alarm floods are commonly *** floods are also identified as the main causes of many industrial *** valid approach to deal with alarm floods is to mine meaningful alarm sequential patterns from alarm *** identified patterns can help to analyze root causes or to configure dynamic alarming *** this paper,a method based on the combination of ClaSP and Top-K is proposed to mine interesting alarm sequential patterns from historical alarm *** contributions of this study are twofold:1) A pattern mining approach is adapted to mine interesting patterns from alarm flood sequences;2) A pattern compression strategy is proposed to reduce pattern redundancy.A case study is presented to demonstrate the effectiveness of the proposed method.
Voice conversion (VC) systems can transform audio to mimic another speaker’s voice, thereby attacking speaker verification (SV) systems. However, ongoing studies on source speaker verification (SSV) are hindered by l...
详细信息
ISBN:
(数字)9798350392258
ISBN:
(纸本)9798350392265
Voice conversion (VC) systems can transform audio to mimic another speaker’s voice, thereby attacking speaker verification (SV) systems. However, ongoing studies on source speaker verification (SSV) are hindered by limited data availability and methodological constraints. This paper presents the Source Speaker Tracking Challenge (SSTC) on STL 2024, which aims to fill the gap in the database and benchmark for the SSV task. In this study, we generate a large-scale converted speech database with 16 common VC methods and train a batch of baseline systems based on the MFA-Conformer architecture. In addition, we introduced a related task called conversion method recognition, with the aim of assisting the SSV task. We expect SSTC to be a platform for advancing the development of the SSV task and provide further insights into the performance and limitations of current SV systems against VC attacks. Further details about SSTC can be found here 1 . 1 https://***/
Rate of penetration(ROP) prediction is crucial for the drilling optimization and cost-savings. In this paper, a novel drilling ROP prediction method is proposed and the prediction model can be divided into two stages(...
详细信息
Rate of penetration(ROP) prediction is crucial for the drilling optimization and cost-savings. In this paper, a novel drilling ROP prediction method is proposed and the prediction model can be divided into two stages(data pre-processing and T-S fuzzy inference modeling). In the first stage, four data pre-processing techniques(Reduction, re-sampling, wavelet filtering, and normalization) are used step by step to improve the quality of drilling data. In the second stage, T-S fuzzy inference method is introduced to establish the ROP prediction model. The experiment is executed by using the data from actual drilling process and the results demonstrate the effectiveness of proposed method in prediction accuracy compared with two conventional methods(response surface method and support vector regression).
Accurate identification of mud pulse signal is crucial for Measurement While Drilling(MWD) system due to its vital role in improving the drilling safety and *** this paper,a pulse position coding-based mud pulse signa...
详细信息
Accurate identification of mud pulse signal is crucial for Measurement While Drilling(MWD) system due to its vital role in improving the drilling safety and *** this paper,a pulse position coding-based mud pulse signal identification algorithm is proposed for MWD system via two *** the signal preprocessing stage,wavelet filtering is introduced to reduce the noises in the raw mud pulse ***,a polynomial fitting-based detection method is used to remove the baseline drift in the *** the signal identification stage,a pulse signal position identification model is established to detect the pulse position,which does not need to set the detection threshold *** comparison results demonstrate that the proposed method has higher identification efficiency and accuracy than the conventional methods.
This paper investigates the finite-time state estimation problem for a class of discrete-time nonlinear singularly perturbed complex networks under a new dynamic event-triggered mechanism(DETM). This new DETM is devis...
详细信息
This paper investigates the finite-time state estimation problem for a class of discrete-time nonlinear singularly perturbed complex networks under a new dynamic event-triggered mechanism(DETM). This new DETM is devised to adjust the date packet transmissions flexibly with hope to save network resources. By constructing a new Lyapunov function dependent on the information of the singular perturbation parameter(SPP) and DETM, a sufficient condition is derived which ensures that the error dynamics of state estimation is finite-time stable. The parameters of the state estimator are given by means of the solutions to several matrix inequalities and the upper bound of the SPP can be evaluated simultaneously. The effectiveness of the designed state estimator is demonstrated by a numerical example.
Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despit...
Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB.
3D formation drillability field is crucial for drilling optimization and control due to its vital role in describing the spatial formation environment. Conventional geostatistical and machine learning methods are intr...
详细信息
3D formation drillability field is crucial for drilling optimization and control due to its vital role in describing the spatial formation environment. Conventional geostatistical and machine learning methods are introduced to establish the ***, the modeling accuracy should be further improved to meet the high-level requirement of drilling engineering. In this paper, a novel deep learning-based spatial modeling method is proposed for 3D formation drillability field. First of all, the drilling process and its characteristics are described and analyzed. After that, long short-term memory(LSTM), a deep learning method is proposed to establish the 3D formation drillability field model. The inputs of the model are the ground and depth coordinates and the output of the model is the formation drillability. Finally, 3D modeling and final test experiments are executed and the drilling data are from Xujiawei area, Northeast China. The results show the effectiveness of proposed method in modeling accuracy compared with four conventional methods(Random forest, Support vector regression, Scattered Interpolation, and Kriging).
In recent years,streaming media services have been widely used in data room management *** order to record the user operations,host machine alarms and reminder in real time,target detection algorithms for streaming me...
详细信息
In recent years,streaming media services have been widely used in data room management *** order to record the user operations,host machine alarms and reminder in real time,target detection algorithms for streaming media have played an important *** target detection methods,limited by detection speed,are not suitable for such real-time ***,in this paper,we applies SSD(Single Shot MultiBox Detector) algorithm to data room management ***,we constructs a host operating image data set,and then perform data amplification by adding noise and ***,the SSD model is used to train a ***,after obtaining the target detection results,the NMS(Non-Maximum Suppression)algorithm is used to avoid the redundant detection *** the same time,some improvement measures are put forward to solve the problem of small target,leading to the difficulty of feature extraction and low detection *** experimental results demonstrate that the model can detect and track the target better in the video and meet the requirements of the real-time performance and accuracy of the system.
In this paper, we focus on the formation control problems of MAS over a directed graph with actuator and communication attacks. The considered system is composed of a leader, some followers and an attacked communicati...
详细信息
In this paper, we focus on the formation control problems of MAS over a directed graph with actuator and communication attacks. The considered system is composed of a leader, some followers and an attacked communication network. Firstly,a new distributed observer is proposed to estimate the leader information despite communication attacks. Then, for high-order nonlinear systems, we develop an adaptive control strategy to solve the actuator attack by using Nussbaum function and backstepping technique, so that the agent with actuator attacks can follow the leader’s trajectory. Finally, a simulation example is proposed to verify the results of this paper.
暂无评论